Triple

T16764475
Position Surface form Disambiguated ID Type / Status
Subject Prague 1 E407427 entity
Predicate contains P35 FINISHED
Object Klementinum E970556 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Klementinum | Statement: [Prague 1, contains, Klementinum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Klementinum
Context triple: [Prague 1, contains, Klementinum]
  • A. Klementinum chosen
    Klementinum is a historic complex in Prague renowned for its Baroque architecture, former Jesuit college, and one of the most beautiful libraries in the world.
  • B. Rudolfinum
    Rudolfinum is a historic neo-Renaissance concert hall and art gallery in Prague, best known as the home of the Czech Philharmonic Orchestra.
  • C. Old Town Hall, Prague
    Old Town Hall in Prague is a historic Gothic complex on the Old Town Square, renowned as a major city landmark and the site of the famous Prague Astronomical Clock.
  • D. Prague 2 Town Hall
    Prague 2 Town Hall is the main local government building and administrative center serving the Prague 2 district of the Czech capital.
  • E. New Town Hall (Prague)
    New Town Hall (Prague) is a historic Gothic municipal building in Prague’s New Town, notable as a former seat of city administration and the site of the first Prague defenestration.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d8839174188190909f190097207065 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3abef492c8190880d3b39c3641eed completed April 18, 2026, 4:06 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00aaf7908481909af31fc2d02f33fb completed May 10, 2026, 3:57 p.m.
Created at: April 10, 2026, 5:21 a.m.